Add MMLU-ProX task (#2811)

* update mmlu_prox configs * update tasks/README * correct hyphon to underline in task/README * update pre-commit codes

Add MMLU-ProX task (#2811)
* update mmlu_prox configs * update tasks/README * correct hyphon to underline in task/README * update pre-commit codes
8aeff141 · heli-qi · GitHub · 8028a42f · 8aeff141 · 8aeff141
Unverified Commit 8aeff141 authored Mar 21, 2025 by heli-qi Committed by GitHub Mar 21, 2025
20 changed files
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_economics.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_economics.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_engineering.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_engineering.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_health.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_health.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_history.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_history.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_law.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_law.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_math.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_math.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_other.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_other.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_philosophy.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_philosophy.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_physics.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_physics.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_psychology.yaml
+++ b/lm_eval/tasks/mmlu_prox/sw/mmlu_prox_sw_psychology.yaml
--- a/lm_eval/tasks/mmlu_prox/sw/utils.py
+++ b/lm_eval/tasks/mmlu_prox/sw/utils.py
--- a/lm_eval/tasks/mmlu_prox/template/_lang_template_yaml
+++ b/lm_eval/tasks/mmlu_prox/template/_lang_template_yaml
--- a/lm_eval/tasks/mmlu_prox/template/utils.py
+++ b/lm_eval/tasks/mmlu_prox/template/utils.py
--- a/lm_eval/tasks/mmlu_prox/th/_mmlu_prox_th.yaml
+++ b/lm_eval/tasks/mmlu_prox/th/_mmlu_prox_th.yaml
--- a/lm_eval/tasks/mmlu_prox/th/_th_template_yaml
+++ b/lm_eval/tasks/mmlu_prox/th/_th_template_yaml
--- a/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_biology.yaml
+++ b/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_biology.yaml
--- a/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_business.yaml
+++ b/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_business.yaml
--- a/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_chemistry.yaml
+++ b/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_chemistry.yaml
--- a/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_computer_science.yaml
+++ b/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_computer_science.yaml
--- a/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_economics.yaml
+++ b/lm_eval/tasks/mmlu_prox/th/mmlu_prox_th_economics.yaml